© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5597
    Prev
    Next
    INDEX
    Explanations

    mentions of Hong Kong

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Urqu
    -0.38
     BorderSide
    -0.35
     Obtén
    -0.33
    ổi
    -0.33
    ecycle
    -0.31
     sti
    -0.31
    徊
    -0.31
    ffix
    -0.30
    Percy
    -0.29
     precedentes
    -0.29
    POSITIVE LOGITS
     Kong
    1.01
    Kong
    0.86
     kong
    0.79
     KONG
    0.77
    VersionUID
    0.64
    脚注の使い方
    0.58
     Hong
    0.57
    adaptiveStyles
    0.57
    rungsseite
    0.56
     CONGRESS
    0.56
    Activations Density 0.207%

    No Known Activations